> For the complete documentation index, see [llms.txt](https://docs.cherry-ai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherry-ai.com/docs/zhong-wen-fan-ti/pre-basic/providers/groq.md).

# Groq

Groq（注意：唔係 xAI 嘅 Grok）係一個以 **LPU 硬件加速、超低延遲** 見長嘅推理服務，主要託管 Llama / Mixtral / Whisper 等開源模型，輸出速度通常係普通雲推理嘅幾倍。

## 拎 API Key

* 去 [GroqCloud](https://console.groq.com/) 註冊帳號
* `API 金鑰` → `建立 API 金鑰`，複製 `gsk_...` 密鑰

## 喺 Cherry Studio 設置

* 打開 `設定 → 模型服務`，搵到 **Groq** Provider 入去詳情頁
* **API 密鑰** 填入 `gsk_...`
* **API 地址** 預設 `https://api.groq.com/openai/v1`，唔使修改
* 撳 **獲取模型列表**

## 推薦用法

| 模型                        | 適合場景       |
| ------------------------- | ---------- |
| `llama-3.3-70b-versatile` | 通用對話，速度極快  |
| `llama-3.1-8b-instant`    | 簡單任務，毫秒級響應 |
| `mixtral-8x7b-32768`      | 長上下文       |
| `whisper-large-v3`        | 語音轉文字      |

## 適用場景

* **即時聊天機械人**：Groq 嘅「幾乎瞬時響應」好適合 IM 接入（配搭 [頻道](/docs/zhong-wen-fan-ti/advanced-basic/agent-channels.md)）
* **大量並發**：每秒 token 數顯著高過普通雲推理
* **唔介意模型係咪最新**：Groq 主要託管 Llama 系等開源模型，冇 GPT-5 / Claude-4 呢類閉源模型

## 區分 Grok vs Groq

|    | [Grok](/docs/zhong-wen-fan-ti/pre-basic/providers/grok.md) | Groq            |
| -- | ---------------------------------------------------------- | --------------- |
| 公司 | xAI（馬斯克）                                                   | Groq Inc.       |
| 主打 | 自研大模型 + 聯網                                                 | LPU 硬件 + 開源模型推理 |
| 模型 | `grok-4` 等自研                                               | `llama-3.x` 等開源 |

{% hint style="warning" %}
Grok（xAI）同 Groq 經常俾人混淆。在 Cherry Studio Provider 列表入面係兩個獨立條目，請注意區分。
{% endhint %}

***

### 💡 獲取幫助同提交反饋

如果您喺配置或使用過程中遇到任何疑問、Bug 或有功能改進建議，請參考 [反饋同建議](/docs/zhong-wen-fan-ti/question-contact/suggestions.md) 入面提供嘅官方渠道。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cherry-ai.com/docs/zhong-wen-fan-ti/pre-basic/providers/groq.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.